Image processing

As mentioned, this can be performed using the LEADTOOLS SDK.  If you're interested only in whether a given image contains a specific intensity value, consider examining the histogram of the image.

https://www.leadtools.com/help/leadtools/v20/dh/pc/histogramcommand.html

 

For example, this code snippet shows how to load an image, generate the histogram, and return based on whether at least one red pixel is present.

 

public static bool UseHistogramCommand(string filePath)

{

using (RasterCodecs codecs = new RasterCodecs())

{

    RasterImage image = codecs.Load(filePath);

 

    HistogramCommand hc = new HistogramCommand();

    hc.Channel = HistogramCommandFlags.Red;

    hc.Run(image);

 

    return hc.Histogram[255] > 0;

}

}

 

Note disk read operations are relatively slow compared to data processing.  At 100 images per second this would limit 10 milliseconds per image.  If these are large images, the bottleneck would be disk.

This depends on different factors, such as: images size, images BPP, Images Formats, etc.  If the images are large on disk, then your bottleneck will be disk.  If small, then you may want to use multi-threading to use all of the cores.
In all cases, you might be able doing this by using one of the following approaches:
1. Read the images data pixel-by-pixel and compare the pixel's color with your color. This is going to be slow, especially of the last pixel is the color you are looking for.
2. Use an SDK like LEADTOOLS that has optimized image processing functions. (Found this on Google, http://support.leadtools.com/CS/forums/6298/ShowPost.aspx)
3. If all images are palettized (contains palette), then you might be able create a custom solution to search the image's palettes without loading them.

A nice article is given over here :

http://www.c-sharpcorner.com/UploadFile/0f68f2/color-detecting-in-an-image-in-C-Sharp/

Please have a look.